JP2023531826A - Method, apparatus and computer program for vehicle - Google Patents

Abstract

The present invention relates to methods, apparatus and computer programs for vehicles and, more particularly, to methods, apparatus and computer programs for determining the location of other vehicles based on received crowd recognition messages. The method includes receiving (110) one or more population recognition messages. Each mass recognition message contains information regarding the absolute position of the vehicle generating the mass recognition message and the relative position of one or more other vehicles that are recognized by the vehicle generating the mass recognition message. The method includes using the locations received in one or more of the population recognition messages to locate (120) on a map each vehicle generating the population recognition message and one or more other vehicles recognized by the vehicle generating the population recognition message. The method includes correlating (130) the positions of the vehicles on the map with the road course on which each vehicle is traveling, and correcting (140) each position based on the correlation between the road course and the positions of the vehicles.

Description

The present invention relates to methods, apparatus and computer programs for vehicles and, more particularly, to methods, apparatus and computer programs for determining the location of other vehicles based on received crowd recognition messages.

Direct communication between mobile devices, also referred to as device-to-device (D2D) communication, vehicle-to-vehicle (V2V) communication, or car-to-car (C2C) communication, continues to be a developing feature of new generation mobile communication systems. By enabling direct communication between vehicles, low latency message exchange can be enabled. Such messages can be used to share information between road participants.

One type of message exchanged between vehicles is a "collective recognition message" (CPM), which is standardized by the European Telecommunications Standards Institute (ETSI). The message here contains an abstract representation of the environment of the vehicle that generates the CPM. Such messages can be used to recognize other vehicles that are not currently within the vehicle's sensor reach. In CPM, other objects, such as other vehicles, are generally referenced relative to the position of the vehicle generating the CPM. In other words, the CPM may contain the position of the transmitting vehicle in absolute coordinates and may contain information about objects relative to the transmitting vehicle detected by the vehicle's sensors. These objects can be other road users, in particular other vehicles. Information about pedestrians can also be transmitted in the form of CPM objects. These topics have been addressed in various research projects and are important applications for increasing traffic safety, for example for roadside sensor systems permanently installed at intersections. Additionally, information about static objects may be transmitted as CPM objects, eg road work barriers.

It would be desirable to provide improved concepts for determining the location of other vehicles based on received crowd recognition messages.

These needs are met by the subject matter of the respective independent claims.

Embodiments of the present disclosure are based on the discovery that while the relative position of other vehicles referenced in the CPM can be reasonably accurate with respect to the vehicle generating the CPM, it can lead to inaccuracies in vehicle position determination when the absolute position of the vehicle generating the CPM is determined via a satellite positioning system. For example, both the absolute position and direction of travel of the vehicle generating the CPM may be less accurate, in which case the position of other vehicles defined relative to the position of the vehicle generating the CPM may be slightly off in the perception of the vehicle receiving the CPM. Embodiments may seek to overcome these limitations by correlating both the position of the vehicle generating the CPM and the position of the vehicle referenced in the CPM to the road course and correcting the position accordingly.

Embodiments provide a method for a vehicle. The method includes receiving one or more collective recognition messages. Each mass recognition message contains information regarding the absolute position of the vehicle generating the mass recognition message and the relative position of one or more other vehicles that are recognized by the vehicle generating the mass recognition message. The method includes using the positions received in one or more of the population recognition messages to locate on a map each vehicle generating the population recognition message and one or more other vehicles recognized by the vehicle generating the population recognition message. The method includes correlating the location of the vehicles on the map with the road course on which each vehicle is traveling. The method includes correcting each position based on the correlation between the road course and the vehicle's position. By using both the position of the vehicle generating the CPM and the position of the vehicle referenced in the CPM, each position can be corrected with high accuracy, for example by co-translating and/or rotating each vehicle relative to the map.

In some embodiments, the positions of the vehicle are not (only) viewed as discrete positions, but rather as the trajectory of the vehicle traveling on the road. Accordingly, the method may include tracking vehicle positions received in one or more of the collective recognition messages to determine the vehicle's trajectory. The vehicle trajectory can be correlated with the road course on which the respective vehicle is traveling. The vehicle's respective position can be corrected based on the correlation between the road course and the vehicle's trajectory. This can further improve accuracy while reducing the effort required to correlate position and road course over time.

For example, correlating the trajectory of the vehicle with the road course may include, for each position, determining a confidence region around the position; and for each trajectory, determining a confidence region around the trajectory based on the confidence region around the position of the trajectory. Each position on the map can be corrected using a confidence region around the trajectory, eg by limiting the correlation to that confidence region. For example, the confidence region around the trajectory can be viewed as a "confidence tube" around the trajectory that shrinks over time and thus can become more accurate.

In general, messages exchanged between vehicles may contain temporary identifiers that change periodically to avoid long-term tracking of vehicles while allowing short-term identification. For example, each collective recognition message may include an identifier for the vehicle generating the collective recognition message. The identifier can be changed to a newly generated identifier according to a predetermined schedule. The method may include determining a match between locations received in population recognition messages having newly generated identifiers and previously determined trajectories, and subsequently using received population awareness messages including the newly generated identifiers to continue tracking respective locations and determining respective trajectories. In other words, if the vehicle's identifier changes, the method may attempt to determine a match between the newly generated identifier and the previously determined trajectory in order to continue tracking the trajectory.

In various embodiments, vehicle positions and/or trajectories on the map derived from the same mass recognition message are both correlated with the road course. For example, the positions and/or trajectories of vehicles on the map from the same mass recognition message may be co-translated and/or rotated relative to the map for correlation of the respective vehicles and road courses. This reduces the effort required for correlation when the vehicle remains in a static configuration and can improve accuracy.

In various embodiments, the position and/or trajectory of the vehicle on the map can be correlated with the road course based on one or more lanes of the road. Additionally or alternatively, the position and/or trajectory of the vehicle on the map can be correlated with the road course based on one or more traffic rules on the road. Both road lanes and respective traffic rules can provide meaningful contextual information for correlation.

In general, the corrected position can be used by the vehicle to identify other vehicles in its vicinity. For example, the method may include determining the position of one or more vehicles in the vicinity of the vehicle via one or more sensors of the vehicle. The method may include determining a relationship between the vehicle on the map and one or more vehicles in the vicinity of the vehicle based on the corrected position of the vehicle on the map. For example, a vehicle on the map can be matched with one or more vehicles in its vicinity based on its corrected position. By using the vehicle's corrected position on the map, determining the relationship between each position may be easier and/or more accurate.

In some embodiments, additional information about one or more vehicles in the vehicle's vicinity may be determined using the vehicle's sensors. This information can be in addition to information previously known for each vehicle. In other words, the method may include supplementing information about the vehicle on the map based on the determined relationship between the vehicle on the map and one or more vehicles in its vicinity.

In some cases, the same vehicle may be recognized by multiple vehicles and thus included in multiple collective recognition messages. Thus, the method can match vehicles that are perceived by multiple vehicles on the map. In other words, at least a first mass recognition message can be received from a first vehicle and a second mass recognition message can be received from a second vehicle. The method may include matching the vehicle referenced in the first population recognition message and the vehicle referenced in the second population recognition message based on the positions included in the respective population recognition messages and/or based on the corrected positions of the vehicles.

In various embodiments, the corrected position can be used to assist the vehicle's autonomous or semi-autonomous navigation among other vehicles. In other words, the method may include operating the vehicle in an autonomous or semi-autonomous driving mode using the vehicle's corrected position on the map.

Embodiments of the present disclosure further provide corresponding computer programs having program code for performing the presented methods when run on a computer, processor or programmable hardware component.

Embodiments of the present disclosure also provide corresponding apparatus for vehicles. The device comprises an interface for receiving group recognition messages from other vehicles. The apparatus comprises a processing module configured to carry out the methods described above. Embodiments further provide a vehicle comprising the apparatus and/or a vehicle configured to carry out the method.

Several other features or aspects are described, by way of example only, using the following non-limiting embodiments of apparatus or methods or computer programs or computer program products and with reference to the accompanying drawings.

1 is a flow chart illustrating one embodiment of a method for a vehicle; 4 is a flow chart illustrating another embodiment of a method for a vehicle; 1 is a block diagram illustrating one embodiment of an apparatus for a vehicle; FIG.

Various exemplary embodiments will now be described in greater detail with reference to the accompanying drawings, in which some exemplary embodiments are shown. In the drawings, the thickness of lines, the thickness of layers, or the thickness of regions may be exaggerated for the sake of clarity. Optional components have been indicated using dashed, dashed or dotted lines.

Accordingly, while example embodiments are capable of various modifications and alternative forms, several embodiments thereof have been shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the exemplary embodiments are not intended to be limited to the particular forms disclosed, but rather the exemplary embodiments cover all modifications, equivalents, and alternatives falling within the scope of the invention. Like reference numbers refer to like or similar elements throughout the description of the figures.

As used herein, the term "or" shall refer to a non-exclusive "or" unless otherwise indicated (eg, "or otherwise" or "or alternatively"). Moreover, as used herein, terms used to describe relationships between elements are to be interpreted broadly, either to include a direct relationship or to include the presence of intervening elements, unless otherwise indicated. For example, when an element is referred to as being “connected” or “coupled” to another element, that element may be directly connected or coupled to the other element or there may be intervening elements. In contrast, when an element is referred to as being "directly connected to" or "directly coupled with" another element, there are no intervening elements present. Similarly, words such as "between" and "adjacent to" should be construed in a similar fashion.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular form "a", "an", "the" is intended to include the plural as well, unless the context clearly indicates otherwise. Further, it will be understood that the terms “comprises,” “comprising,” “includes,” or “including,” as used herein, prescribe the presence of the recited feature, integer, step, action, element or component, but do not exclude the presence or addition of one or more other features, integers, steps, actions, elements, components, or groups thereof.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the exemplary embodiments belong. Moreover, it is to be understood that terms defined, for example, in commonly used dictionaries, are to be construed to have a meaning consistent with their meaning in the context of the relevant field, and are not to be construed in an ideological or overly formal sense unless explicitly so defined herein.

1a and 1b show a flowchart of an embodiment of the method for vehicle 100. FIG. The method includes receiving 110 one or more collective recognition messages (CPMs). Each mass recognition message contains information regarding the absolute position of the vehicle generating the mass recognition message and the relative position of one or more other vehicles recognized by the vehicle generating the mass recognition message. The method includes locating 120 on a map each vehicle generating the population recognition message and one or more other vehicles recognized by the vehicle generating the population recognition message using the locations received in the one or more population recognition messages. The method includes correlating 130 the location of the vehicles on the map with the road course on which each vehicle is traveling. The method includes correcting 140 each position based on the correlation between the road course and the position of the vehicle.

FIG. 1c shows a block diagram of one embodiment of a corresponding device 10 for a vehicle. The device 10 comprises an interface 12 for receiving group recognition messages from other vehicles 200 . The apparatus comprises a processing module 14 configured, for example in conjunction with the interface 12, to carry out the method of Figures 1a and/or 1b. The processing module 14 is connected with the interface 12 and optionally with one or more recognition sensors (not shown) of the vehicle. FIG. 1c further shows a vehicle 100 with the device 10. FIG.

The following description relates to the method of FIGS. 1a and/or 1b and the corresponding apparatus 10 or vehicle 100. FIG.

Various embodiments of the present disclosure relate to methods, apparatus and computer programs for vehicles, eg, so-called "connected" vehicles, i.e. vehicles equipped with an interface 12 for communicating with other vehicles in the vicinity. In the context of this application, such vehicles are sometimes referred to as V2X vehicles, ie vehicles equipped with V2X (Vehicle-to-Anything) communications. Such vehicles can communicate directly with each other, ie without involving a base station transceiver, also referred to as vehicle-to-vehicle (V2V) communication, device-to-device (D2D) communication. Technologies that enable such D2D/V2V or V2X communication include 802.11p and beyond, Third Generation Partnership Project (3GPP) systems (4G (fourth generation), 5G (fifth generation), NR (NewRadio) and beyond), etc.). For example, vehicles exchange predetermined messages, such as CPM, Cooperative Awareness Messages (CAM) or Distributed Environment Notification Messages (DENM). The content of such messages enables the recipient to become aware of his environment and to determine a map of the vehicle environment. By way of example, the vehicle 100 may also be referred to as the ego vehicle since the perspective of the proposed concept focuses on the vehicle.

Various embodiments of the present disclosure relate to concepts for associating CPM objects with the ego-vehicle's environment model with the help of prior knowledge. In general, a CPM includes an abstract representation of the environment of the vehicle generating the CPM as perceived by the vehicle generating the CPM. In CPM, other objects, such as other vehicles, are referenced, generally relative to the location of the vehicle generating the CPM. In other words, the CPM may include the position of the sending vehicle (i.e., the vehicle generating the CPM) in absolute coordinates and information about objects detected by vehicle sensors relative to the sending vehicle. Objects here can be other road users, in particular other vehicles. It is also possible to transmit information about pedestrians in the form of CPM objects. The proposed concept can be restricted to vehicles other than CPM objects. Thus, each mass recognition message contains information about the absolute position (i.e., absolute coordinates) of the vehicle generating the mass recognition message and information about the relative position (i.e., coordinates relative to the vehicle generating the CPM) of one or more other vehicles that are recognized by the vehicle generating the mass recognition message (using the recognition sensors of said vehicles).

Assignment between the CPM sender's vehicle (i.e., the vehicle generating the CPM message) and the CPM objects (referenced in the CPM) detected by the CPM sender's vehicle to objects detected by the receiving vehicle itself is usually very difficult and often impossible. The reason is that vehicles on the CPM transmitting side often cannot determine their own attitude (position and orientation) with sufficient accuracy. Information about CPM objects detected by the CPM transmitting vehicle is correspondingly inaccurate. In addition to inaccuracies in sensor measurement and calibration, errors in estimating vehicle heading (heading) also contribute to this. Angular errors have a particularly large impact in detecting distant objects.

In contrast to some other concepts, the proposed concept can not only focus on the association of vehicles transmitting V2X messages (CAM, DENM, CPM), but also address the association of CPM objects, i.e. vehicles that are transmitted in the CPM and detected by the sensors of the CPM vehicle.

The proposed concept has the following features: - receiving 110 CPM messages;
- storing the received CPM messages, e.g. in a table for creating a history;
- placing 120 the CPM sender's vehicle and its CPM objects on a map (i.e. V2X environment map);
- improving the allocation to lanes and positions based on logical combinations (e.g. by correlating 130 CPM sender vehicles and CPM objects with road courses and correcting 140 map positions accordingly);
- high-level fusion 150 of vehicles detected by the ego vehicle and corresponding CPM objects from the V2X environment map;
may include one or more of

To use the proposed method, the receiving vehicle (i.e. vehicle 100):
- a V2X receiver unit (e.g. interface 12) enabling reception of CPM, CAM and DENM,
- digital maps with sufficient accuracy, e.g. high-definition maps (representing road courses);
- a system for localization (e.g. GPS receiver),
- sensor systems for object detection, e.g. cameras, LiDAR, radar, etc.
- a computing unit (e.g. a processing module) for computing the environment model and associating the V2X vehicle and the CPM object;
may include one or more parts of each device of

To perform association, one or more of the following measures are taken.

A V2X environment map can be created. In the context of this application, the V2X environment map can also be referred to as the map on which the respective vehicle is located. In some embodiments, the vehicle's location referenced in the CPM message can be stored in a V2X environment table, and the V2X environment table can be used to generate the map. Based on the received CPM message, the position of the sending vehicle (where it has its confidence ellipse/region) and the direction of travel of the vehicle can be stored in the V2X environment table. In addition, CPM objects can be stored in the table along with their confidence level definitions defined in the CPM (e.g. confidence level definitions in the x, y and z directions relative to the coordinate system of the CPM vehicle, hereinafter referred to as confidence distances). The ordering criteria for the table can be the sender's pseudonym (ie, the identifier included in the CPM message) and the transmission time. The V2X environment table may be updated periodically. Updates can be limited to a predetermined period of time, eg, the last 30 seconds. As with circular buffers, unused information can be replaced by new information and stored elsewhere as needed. The contents of the V2X environment table can be input into the digital map. In other words, the method includes locating 120 on a map each vehicle generating the population recognition message and one or more other vehicles recognized by the vehicle generating the population recognition message using the locations received in the one or more population recognition messages. For example, the positions received in one or more collective recognition messages may include, for each CPM, the absolute position of the vehicle generating the CPM and one or more relative positions to the absolute position of the vehicle generating the CPM for one or more other vehicles. For example, the (V2X environment) map may be a static map containing paths of one or more roads, intersections, traffic infrastructure (traffic lights, signs, crosswalks, etc.), buildings, and the like.

The (V2X environment) map may include static and dynamic objects within the vehicle environment along at least a portion of the vehicle's trajectory. That portion of the trajectory may be, for example, the portion that the vehicle plans to travel in the next 30 seconds, 1 minute, 5 minutes, 10 minutes, and so on. Dynamic objects are objects that are not persistently stationary/fixed, such as other road participants, pedestrians, vehicles, etc., but can also be semi-static objects, such as moving construction sites, traffic signs representing narrow sections of roads or lanes. For example, such dynamic objects can be other vehicles, pedestrians, cyclists, road participants, and the like. When determining an environment model, not all objects in the model can be determined with the same degree of confidence. There are objects that can achieve higher certainty than others. For example, if multiple CPMs or sensors were able to identify or confirm a given object, its presence and/or its state of motion could potentially be determined with greater confidence than if only data from a single CPM or sensor were indicative of the object.

In the CPM sender's vehicle, the trajectory and confidence tube (ie, the confidence region around the trajectory) for the route traveled by the vehicle can be derived from the vehicle's position and/or the confidence ellipse. In other words, the method may include tracking 122 the position of the vehicle received in one or more mass recognition messages to determine 124 the trajectory of the vehicle. For example, a vehicle trajectory can be derived from the vehicle's individual positions over time. The method may include, for each location, determining a confidence region around that location. For example, a CPM can have information about the confidence of the absolute position of the vehicle generating that CPM, which can be used to generate a confidence region around that position. For the path traveled by each CPM object, the x-, y-, and z-confidence distances included in the CPM may yield a trajectory with a confidence tube (i.e., a confidence region around the trajectory). If the confidence changes during the observation period, the width of the confidence tube can be changed. The method may include determining, for each trajectory, one confidence region around the trajectory (e.g., by combining the confidence regions around the position) based on the confidence regions around the positions of the trajectories. These can be used later to correct the position on the map, for example by restricting the correlation to a confidence region around the position or trajectory. In other words, each position on the map can be corrected using a confidence region around the trajectory. Each confidence tube may contain a trajectory obtained from the position transmitted with the CPM. The trajectory of a recognized CPM object can be derived from its individual positions or can be constructed from its individual positions. Trajectories can be supplemented by confidence tubes. If individual CPM messages were not received, the missing positions can be estimated or interpolated from neighboring values, eg by averaging. The position of the transmitting V2X vehicle can be defined as absolute coordinates in the CPM. CPM object (trajectory, confidence tube) values can be relative to the CPM object. Outliers can be discarded and a best fit of the trajectory and confidence tube (to the lane of the road) can be done in case of messages not received.

In many cases, trajectories may not be explicitly assigned to lanes on the map. Thus, in a separate step, corrections can be made using, for example, ontology or logical relationships using rules, and trajectories and confidence tubes can be moved. The method includes correlating 130 the location of the vehicles on the map with the road course on which each vehicle is traveling. For example, correlating a vehicle's position on a map with a road course may include determining how to best fit the vehicle to the road course without violating constraints and/or according to logical relationships, such as without driving between lanes or roadsides or violating traffic rules. That is, based on the correlation between road course and vehicle position, each position is corrected 140 accordingly. For example, the correlation between the road course and the position of the vehicle can relate to the position of the vehicle relative to the road course that best fits the constraints and/or logical relationships. The corrected trajectory/position values and/or confidence tube values can be stored in a second table. A table with initial values can be kept so that it can be made available later, eg for control purposes or further corrections. The probability of correctness for each correction is estimated and stored, which can then be processed during association.

Section-by-section corrections of the trajectory and confidence tube can be performed when there is a jump in the position data of the transmitting vehicle (i.e. the vehicle generating the CPM), for example caused by self-position measurement errors (possible with GPS systems for example). The CPM object trajectory and confidence tube can be corrected accordingly.

One or more of the following logical relationships, among others, can be used for corrections for CPM vehicles and CPM objects.

For example, the correction can take into account traversable and impassable regions (shown here) on the map. For example, vehicles cannot pass through buildings or by bridges. In other words, the vehicle's position is correlated with the road course. The position and/or trajectory of the vehicle on the map can be correlated with the road course based on one or more lanes of the road. Additionally or alternatively, the correction can take into account logical relationships when moving CPM objects as a group. The CPM sender's vehicle and its CPM object form a group that can be inserted into the map as a whole by translation and rotation. In other words, vehicle positions and/or trajectories on the map derived from the same collective recognition message can both be correlated to the road course. In other words, during correlation, vehicle positions and/or trajectories on the map that originate from the same mass recognition message can retain their positions relative to each other. For example, the positions and/or trajectories of vehicles on the map derived from the same mass recognition message can be co-translated and/or rotated relative to the map to correlate the respective vehicles and road courses. Additionally or alternatively, the correction may also take into account logical relationships derived from the shape of the trajectory, for example from the radius or distance traveled to a salient point such as the start of a curve. Additionally or alternatively, the correction can also take into account the traffic rules in force. These can be used for validation and to determine the probability of correctness of the correction. In other words, the vehicle's position and/or trajectory on the map is correlated with the road course based on one or more traffic rules on the road.

As pointed out above, when correlating position and road course, not only the position of the vehicle but also its trajectory can be considered. In other words, the trajectory of the vehicles can be correlated 130 with the road course on which each vehicle is traveling. The vehicle's respective position may also be corrected 140 based on the correlation between the road course and the vehicle's trajectory.

In addition to the V2X environment map, another map or model may be generated, which may also be referred to as an object environment map. The creation of the object environment map will be described below. In parallel with the above steps for creating a V2X environment map, the vehicle can use its own sensors to detect objects in its environment on a regular basis. The method may include determining 150 the position of one or more vehicles in the vicinity of the vehicle via one or more sensors of the vehicle. For example, a vehicle may include visual/optical sensors (cameras), radar sensors, ultrasonic sensors, LiDAR (light detection and ranging) sensors, or other sensors. The object environment map may be a digital model of the vehicle environment based on vehicle sensor data. A vehicle can use the sensor data to model its surroundings.

Generating an object environment map can include measurement inaccuracies in object detection and inaccuracies in self-localization. The location of each object can be entered into an object environment table and/or an object environment map. For each vehicle a history of observed distances traveled (trajectory, position-time progression) can also be stored. Egotrajectories and confidence tubes can also be included in the object environment map. The object environment table or object environment map can be updated periodically.

In the following, we discuss matching objects from the object map with objects from the V2X environment map. For example, a vehicle in the object environment map can now be compared with a vehicle from the corresponding region of the V2X environment map. Since the range of V2X communication is often larger than the sensor range, the environment map may typically contain only a subset of the V2X environment map. The trajectories of objects detected by the sensors can be compared with the trajectories of V2X objects (CAM sender, DENM sender, CPM sender vehicle and CPM objects). In other words, the method may include determining 160 a relationship between the vehicle on the map and one or more vehicles in its vicinity based on the corrected position of the vehicle on the map. For example, a vehicle on the map can be matched with one or more vehicles in its vicinity based on the vehicle's corrected position on the map. Statistical methods can be used for this. Among other things, spatial trajectories and velocity profiles can be considered. The assignment can be made from a defined threshold (eg a measure of correlation), ie V2X transmitters or CPM objects can be assigned to detected vehicles. Such assignments can also take into account information contained in the V2X messages, such as vehicle class (truck, car). The allocation can also take into account the probability of correcting the trajectory of the V2X vehicle. Information collected via sensors may be used to augment the information contained in the V2X environment map. Accordingly, the method may include supplementing 162 information about vehicles on the map based on the determined relationship between the vehicle on the map and one or more vehicles in its vicinity, for example by improving the accuracy of the position and/or trajectory of each vehicle.

A CPM object may be a CAM (Cooperative Awareness Message) sender vehicle, or a DENM (Decentralized Environmental Notification Message) sender vehicle, or other CPM sender vehicle. Also, one vehicle may have been identified as a CPM object by multiple CPM sender vehicles. For example, at least a first mass recognition message can be received from a first vehicle and a second mass recognition message can be received 110 from a second vehicle. Accordingly, in various embodiments, resolving such ambiguities and determining matches between vehicles can be a task. In other words, the method may include matching 170 the vehicles referenced in the first population recognition message and the vehicles referenced in the second population recognition message based on the positions included in the respective population recognition messages and/or based on the corrected positions of the vehicles. In various embodiments, corrected map entries can be used for this purpose. In a first step, the affected V2X vehicle or CPM object can be identified. For example, a measure of spatial proximity or overlap of trajectories and confidence tubes can be used for this purpose. Criteria that allow validation of the same object can then be considered. Suitable criteria are, for example, a comparison of speed-time curves (starting to decelerate at the same time) or angle-time curves for changes in vehicle orientation (direction of travel). Furthermore, information contained in the V2X message such as vehicle class (truck, passenger car) can be taken into account. Statistical methods can be used here. The assignment can be made from a defined threshold (eg a measure of correlation).

Ambiguity can be removed from the map. Erased objects can be saved in a separate table to allow later inspection and correction. For example, objects that remain in the map can be marked as having been detected multiple times. In some embodiments, multiple detections of individual objects may occur over longer periods of time. Because, for example, these results result from the fact that traffic and vehicle flows operate substantially parallel to each other. In this case the plausibility check can be simplified, eg only at intervals defined as periodic checks. When removing duplicates, an evaluation can also be made of which objects have been removed and which objects have been retained. To this end, an assessment can be made as to which information is likely to be more accurate. The less accurate ones can be deleted. In some embodiments, a correction of the object's position is performed during this step and only the corrected values are left in the map.

Typically, each mass recognition message includes an identifier for the vehicle generating the mass recognition message. The identifiers can change to newly generated identifiers according to a predetermined schedule (which may be static or based on the number of vehicles in the vicinity). If the pseudonym is changed (by generating a new identifier), the V2X vehicle will disappear and a new vehicle will be created. Therefore, a plausibility check can be performed to ensure that both vehicles are identical. The method may include determining 126 a match between locations received in population recognition messages with newly generated identifiers and previously determined trajectories. For example, a match can be confirmed if the position received in the population recognition message with the newly generated identifier is an extension of the previously determined trajectory. The method may include tracking 122 each location and continuing to determine each trajectory using subsequently received population recognition messages including the newly generated identifier. For example, if a re-evaluation of the new vehicle is not allowed by driving with the same sensor set and objects and road courses recognized by the same old pseudonym as the new pseudonym, then it is likely that the same vehicle is involved.

The generated V2X environment can be used to operate the vehicle. In other words, the method may include operating 180 the vehicle in an autonomous or semi-autonomous driving mode using the corrected vehicle position on the map. For example, a map containing corrected positions can be used by a vehicle to determine the position of other vehicles in its vicinity, its (projected) trajectory and/or distance to other vehicles, which can be used to plot the course of the vehicle on the road.

In embodiments, interface 12 may correspond to any means of obtaining, receiving, transmitting or providing analog or digital signals or information, e.g., any connector, contact, pin, register, input port, output port, conductor, lane, etc. that allows for providing or obtaining signals or information. The interface can be wireless or wired, and can be configured to communicate, ie, send and receive signals, information to and from another internal or external component. The interface 12 may comprise further components communicatively enabled, for example in a mobile communication system, such as components of a communication device (transmitter and/or receiver), such as one or more low noise amplifiers (LNA), one or more power amplifiers (PA), one or more duplexers, one or more diplexers, one or more filters or filter circuits, one or more converters, one or more mixers, correspondingly adapted radio frequency components. and so on. Interface 12 is connectable to one or more antennas, which may correspond to any transmit and/or receive antenna, such as horn antennas, dipole antennas, patch antennas, sector antennas, and the like. The antennas can be arranged in defined geometric settings, such as uniform arrays, linear arrays, circular arrays, triangular arrays, uniform field antennas, field arrays, combinations thereof, and the like. In some embodiments, interface 12 can be used to transmit or receive information, such as information related to capabilities, control information, payload information, application requirements, trigger indications, requests, messages, data packets, acknowledgment packets/messages, etc.

As shown in FIG. 2a, an interface 12 is connected to each processing module 14 in the device 10. FIG. In embodiments, the processing module 14 may be implemented using one or more processing units, one or more processing devices, any processing means, such as a processor, computer, or programmable hardware component operable by correspondingly adapted software. In other words, the functionality described for processing module 14 may be implemented as software, where the software is executed in one or more programmable hardware components. Such hardware components may include general purpose processors, digital signal processors (DSPs), microcontrollers, and the like.

In embodiments, communication, i.e. transmission or reception or transmission and reception, may occur directly between vehicles and/or between mobile communication devices/vehicles and network components/entities (infrastructure or mobile communication devices such as base stations, network servers, backend servers, etc.). Such communication can utilize a mobile communication system. Such communication can be done directly by, for example, device-to-device (D2D) communication, which in the case of vehicles can also include vehicle-to-vehicle (V2V) communication or car-to-car (C2C) communication, and can be performed using the specifications of mobile communication systems.

In embodiments, interface 12 may be configured for wireless communication in a mobile communication system. For example, direct cellular vehicle-to-anything (C-V2X) communication, including at least V2V, V2 infrastructure (V2I), V2 pedestrian (V2P), transmissions compliant with 3GPP Release 14 or later, etc., may be managed by the infrastructure (so-called mode 3 in LTE) or performed in the UE (so-called mode 4 in LTE).

Various examples of the proposed concept may include recording a trace of the CPM sender's vehicle and the detected objects described in the CPM. Proposed concepts may include the allocation of locations/traces on maps (V2X environment maps) and improved allocation to lanes and locations based on logical relationships for both the vehicle of the CPM sender and the detected objects described in the CPM. Various examples may include recording traces of objects observed by vehicle sensors and assigning these traces to another map (an object environment map). The proposed concept can provide high-level fusion of detected vehicles and corresponding objects from V2X environment maps and evaluation of trace correlations.

As already mentioned, in embodiments each method may be implemented as a computer program or code executable in the respective hardware. Another embodiment is therefore a computer program product having program code for performing at least one of the above methods when run on a computer, processor or programmable hardware component. Another embodiment is a computer-readable storage medium storing instructions that, when executed by a computer, processor, or programmable hardware component, cause the computer to perform one of the methods described herein.

A person of ordinary skill in the art will readily appreciate that a programmed computer can perform the steps of the various methods described above, for example determining or calculating slot positions. As used herein, some embodiments are also intended to cover program storage devices, e.g., digital data storage media that are machine-readable or computer-readable and that encode a program of machine-executable or computer-executable instructions, where the instructions are for performing some or all of the steps of the methods described herein. The program storage device may be, for example, a digital memory, a magnetic storage medium such as a magnetic disk and magnetic tape, a hard disk drive, or an optically readable digital data storage medium. Embodiments are also intended to cover a computer programmed to perform the steps of the methods described herein, or a (field) programmable logic array ((F)PLA) or (field) programmable gate array ((F)PGA) programmed to perform the steps of the methods described above.

The description and drawings are merely illustrative of the basic scheme of the invention. Accordingly, those skilled in the art will appreciate that various devices, even though not explicitly described or illustrated herein, may be devised that embody the basic principles of the invention and are within the spirit and scope of the invention. Further, all examples set forth herein are expressly intended merely for teaching purposes, primarily to assist the reader in understanding the underlying principles of the present invention and the concepts to which the inventors have contributed to advancing the art, and should be considered without limitation to such examples and conditions specifically mentioned. Moreover, all discussions herein of basic schemes, aspects, and embodiments of the invention, as well as specific examples thereof, referred to herein are intended to encompass equivalents thereof. Each function, if provided by a processor, can be provided by a single dedicated processor, by a single shared processor, or by multiple separate processors that may share some functions. Furthermore, any explicit use of the term "processor" or "controller" should not be construed to refer only to hardware capable of executing software, which can implicitly include, but is not limited to, digital signal processor (DSP) hardware, network processors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), read-only memory (ROM) for storing software, random access memory (RAM), and non-volatile storage. Other hardware, conventional or custom hardware may also be included. The functions of these things may be performed through the operation of program logic, or through dedicated logic, or through interaction of program control and dedicated logic, or even manually, and the specific techniques may be selected by those skilled in the art as more specifically understood from the context.

It will be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative circuits embodying the basic principles of the invention. Similarly, it will be understood that any flowchart, flow diagram, state transition diagram, pseudocode, etc., are embodied in a computer-readable medium and represent various processes that are executable by a computer or processor, whether or not such computer or processor is explicitly indicated.

Moreover, the following claims are hereby incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment. While each claim may stand alone as a separate embodiment, it should be noted that even if a dependent claim refers in a claim to a particular combination with one or more other claims, other embodiments may include the subject matter of each other dependent claim in combination with the dependent claim. Unless it is stated that no particular combination is intended, such combinations are proposed herein. Furthermore, even if a claim is not directly dependent on any other independent claim, it is also intended to include the features of the claims to that independent claim.

Furthermore, it should be noted that the methods disclosed in the specification or claims may be implemented by a device having means for performing each of the corresponding steps of those methods.

10 apparatus 12 interface 14 processing module 100 vehicle 110 receive one or more group recognition messages 120 place vehicle on map 122 track position of vehicle 124 determine trajectory of vehicle 126 determine match 130 correlate vehicle position with road course 140 correct respective position 150 determine position of vehicles in proximity to vehicle 160 determine relationships 162 supplement information 170 match vehicles 180 operate vehicles 200 vehicles

Claims (15)

A method for a vehicle (100), the method comprising:
receiving (110) one or more mass recognition messages, each mass recognition message including information regarding the absolute position of the vehicle generating the mass recognition message and the relative position of one or more other vehicles recognized by the vehicle generating the mass recognition message;
locating (120) on a map each vehicle generating the population recognition message and one or more other vehicles recognized by the vehicle generating the population recognition message using the positions received in the one or more population recognition messages;
correlating (130) the position of the vehicle on the map with the road course on which each vehicle is traveling, and correcting (140) each position based on the correlation between the road course and the position of the vehicle;
A method, including The method includes tracking (122) the positions of vehicles received in the one or more population recognition messages to determine (124) vehicle trajectories;
The trajectories of the vehicles are correlated (130) with the road courses on which the respective vehicles are traveling, and the respective positions of the vehicles are corrected (140) based on the correlation between the road courses and the trajectories of the vehicles;
The method of claim 1. correlating (130) the trajectory of the vehicle with the road course comprises, for each location, determining a confidence region around the location; and for each trajectory, determining a confidence region around the trajectory based on the confidence region around the location of the trajectory,
each position on the map is corrected using a confidence region around the trajectory;
3. The method of claim 2. each cluster identification message includes an identifier of the vehicle generating the cluster identification message, the identifier being changed to the newly generated identifier according to a predetermined schedule;
The method comprises determining (126) a match between locations received in population recognition messages having newly generated identifiers and previously determined trajectories, and then continuing to track (122) respective locations and determine respective trajectories using population recognition messages received thereafter containing said newly generated identifiers;
4. A method according to claim 2 or 3. 5. A method according to any one of claims 1 to 4, wherein the vehicle's position and/or trajectory on the map originating from the same mass recognition message are both correlated with the road course. 6. The method of claim 5, wherein the positions and/or trajectories of the vehicles on the map derived from the same mass recognition message are co-translated and/or rotated relative to the map for correlation of each vehicle with the road course. The position and/or trajectory of the vehicle on the map is correlated with the road course based on one or more lanes of a road, and/or the position and/or trajectory of the vehicle on the map is correlated with the road course based on one or more traffic rules on the road.
A method according to any one of claims 1 to 6. 8. The method of any one of claims 1 to 7, wherein the method comprises determining (150) the position of one or more vehicles in the vicinity of the vehicle via one or more sensors of the vehicle, and determining (160) a relationship between the vehicle on the map and one or more vehicles in the vicinity of the vehicle based on the corrected position of the vehicle on the map. 9. The method of claim 8, matching the vehicle on the map with one or more vehicles in the vicinity of the vehicle based on the corrected position of the vehicle on the map. 10. The method of claim 8 or 9, wherein the method comprises supplementing (162) information about the vehicle on the map based on a determined relationship between the vehicle on the map and one or more vehicles in the vicinity of the vehicle. at least a first mass recognition message is received from the first vehicle and a second mass recognition message is received from the second vehicle (110);
The method includes matching (170) a vehicle referenced in the first population recognition message and a vehicle referenced in the second population recognition message based on locations contained in the respective population recognition messages and/or based on corrected locations of the vehicles;
A method according to any one of claims 1 to 10. 12. The method of any one of claims 1 to 11, wherein the method comprises operating (180) the vehicle in an autonomous or semi-autonomous mode using the corrected position of the vehicle on the map. A computer program product having program code for performing the method of any one of claims 1 to 12 when run on a computer, processor or programmable hardware component. A device (10) for a vehicle (100), the device comprising:
an interface (12) for receiving collective recognition messages from other vehicles (200);
a processing module (14) configured to perform the method according to any one of claims 1 to 12;
A device (10) comprising: A vehicle (100) comprising a device (10) according to claim 14.

Images